Claude Skills

This Claude skill applies the Six Thinking Hats methodology to software testing, providing structured perspectives for analyzing test strategies, failures, and discussions. It guides you through distinct lenses like facts, risks, creativity, and process to ensure comprehensive quality analysis. Use it when designing test approaches, conducting retrospectives, or evaluating testing methods.

This skill enables testing in production using feature flags, canary deployments, and chaos engineering. It's designed for implementing production observability and progressive delivery strategies. Key capabilities include progressive rollouts, synthetic monitoring, and failure injection to build system resilience.

This skill helps developers implement shift-left testing by moving validation and test creation earlier in the development lifecycle. It provides actionable steps for practices like TDD, BDD, and CI/CD integration to catch defects when they are cheapest to fix. Use it to structure your testing strategy with a focus on requirements validation, test-first development, and automated pipeline checks.

Sherlock-review is an evidence-based code review skill that uses deductive reasoning to systematically verify implementation claims, investigate bugs, and perform root cause analysis. It guides developers through a process of observation, deduction, and elimination to determine what actually happened versus what was claimed. This skill is ideal for validating fixes, conducting security audits, and performing performance validation.

This Claude Skill systematically tests for security vulnerabilities using OWASP principles, including scanning for injection attacks and validating authentication. It's designed for use during security audits, implementing security practices, or testing authorization. Key capabilities include checking for the OWASP Top 10, dependency vulnerabilities, and exposed secrets.

This Claude skill prioritizes testing efforts by assessing risk through probability and impact analysis. It allocates testing resources proportionally, focusing 60% of effort on critical risks. Use it during test planning and resource allocation to maximize test coverage efficiency.

This skill strategically selects and runs regression tests based on code changes and risk, ensuring fixes don't break existing functionality. It analyzes impact, optimizes test execution for faster feedback, and helps manage continuous regression within CI/CD. Use it for verifying changes, planning test suites, or streamlining test execution.

This Claude Skill applies safe refactoring patterns to improve code structure while preserving behavior, ideal for reducing technical debt and enhancing maintainability. It enforces a disciplined workflow where developers make small, test-verified changes and commit progress incrementally. Key features include a guaranteed safe refactoring cycle and integration with code review and quality analysis agents.

This skill enables AI agents to implement adaptive learning by recording experiences, recognizing patterns, and optimizing strategies over time. Use it when building self-learning agents or meta-cognitive systems that require continuous improvement. It provides persistent learning capabilities through integrations like AgentDB.

This skill implements adaptive learning for AI agents using AgentDB's high-performance vector database. It provides trajectory tracking, verdict judgment, and memory distillation to enable self-improving decision-making systems. Use it when building self-learning agents, optimizing decision processes, or implementing experience replay with 150x faster pattern retrieval.

The quality-metrics skill helps developers establish actionable quality dashboards and KPIs by focusing on outcome-based measurements like DORA metrics. It guides users to avoid vanity metrics, set effective quality gates, and track trends over time. This optimized skill is ideal for evaluating test effectiveness and defining key performance indicators.

This Claude Skill helps developers plan and execute performance tests, including load and stress testing, to identify system bottlenecks. It provides structured guidance for defining SLOs, creating realistic user scenarios, and analyzing key metrics like response time and throughput. Use it when optimizing application scalability, resilience, or overall performance before production.

This skill provides comprehensive performance analysis for Claude Flow swarms, detecting bottlenecks and generating optimization recommendations. It offers real-time profiling, detailed reporting, and AI-powered suggestions to improve swarm operations. Use it when you need to monitor, analyze, and optimize the performance of your Claude Flow applications.

This skill enables AI-assisted pair programming with driver/navigator role management, supporting workflows like TDD, debugging, and refactoring. It provides real-time code verification, quality monitoring, security scanning, and comprehensive testing. Use it for collaborative coding sessions where you need continuous review and truth-score validated outputs.

This skill provides comprehensive testing for n8n workflow automation, covering execution lifecycle, node connections, and data flow validation. It's designed for developers to validate workflow structure, test with realistic data, and verify error handling. Use it when testing n8n automation applications to ensure reliable workflow execution.

This skill provides comprehensive testing strategies for n8n workflow triggers, including webhooks, schedules, and polling mechanisms. It helps developers verify trigger activation, payload handling, authentication, and error responses. Use it when you need to ensure your n8n workflows are triggered reliably and correctly.

This Claude Skill provides automated security testing for n8n workflows, detecting credential exposure, validating OAuth flows, and verifying data sanitization. Developers should use it when validating n8n workflow security to check for insecure configurations and sensitive data handling. It performs critical checks like scanning for credentials in workflow JSON and ensuring proper encryption.

This skill provides testing patterns for n8n workflow integrations, covering API contracts, authentication, rate limiting, and error handling. Use it when developing or validating n8n nodes that connect to external services. It helps ensure integrations are robust and handle real-world scenarios properly.

This skill validates and tests n8n workflow expressions, checking for correct syntax, context-aware scenarios, and common pitfalls. It helps developers optimize performance and ensure safety by detecting issues like null references or security vulnerabilities. Use it when building or debugging n8n data transformations.

The mutation-testing skill evaluates test suite effectiveness by automatically introducing code mutations and measuring the kill rate. It helps developers identify weak tests and improve test quality by revealing which bugs tests actually catch. This specialized-testing skill uses multiple agents to mutate code, run tests against mutants, and highlight areas needing stronger assertions.

This Claude Skill provides comprehensive mobile testing for iOS and Android applications, covering gestures, sensors, permissions, and device fragmentation. Use it when testing native apps, hybrid apps, or mobile web to ensure quality across 1000+ device variants. It focuses on platform differences, real-device validation, and mobile-specific scenarios like offline mode.

This skill automates internationalization and localization testing for global products, including translation coverage, locale-specific formats, and RTL language support. It's designed for developers launching in new markets or building multi-language applications to validate cultural appropriateness and character encoding. Use it to systematically verify i18n/l10n requirements across text, visuals, and regional formats.

Hooks Automation provides intelligent pre/post-operation hooks that coordinate Claude Code workflows with automated validation, formatting, and agent assignment. It integrates with MCP tools for Git operations, session management, and cross-session memory persistence. Use this skill to automate and enhance development workflows through neural pattern learning and performance tracking.

This skill helps developers design comprehensive test strategies by applying the PACT principles (Proactive, Autonomous, Collaborative, Targeted). It is used for building quality into teams and testing Classical, AI-assisted, or Agentic Systems. The skill provides a structured model for implementing whole-team quality practices.